Rumor Discovery - Event Recommendation Engine
Problem
Event discovery lacks personalized mathematical precision
Solution
Advanced vector mathematics and weighted scoring algorithms
Impact
Precise event-user matching using mathematical modeling
Users
25 user personas across 6 industries with 40 curated events
About the Project
An advanced event recommendation engine that leverages sophisticated mathematical algorithms including 5D vector embeddings, cosine similarity calculations, and weighted hybrid scoring to match users with relevant events. The system implements a complex scoring formula: FinalScore = ((Vector × 0.35) + (Audience × 0.40) + (History × 0.25)) × Location × 100, where vector similarity uses cosine distance calculations in 5-dimensional interest space. Features intelligent role aliasing (CEO↔Founder, VC↔Investor), pre-computed explanations for 1,000 user-event combinations, and multi-provider LLM integration. Built with Next.js and TypeScript, the platform demonstrates advanced mathematical modeling, vector space operations, and production-ready recommendation algorithms with comprehensive test coverage including cosine similarity validation, score distribution analysis, and pipeline integration testing.
Key Features
- 5D Vector Embeddings
- Weighted Hybrid Scoring Algorithm
- Cosine Similarity Calculations
- Role Aliasing System
- 1,000 Pre-computed Explanations
- Multi-Provider LLM Integration